{"id":"https://openalex.org/W7155061739","doi":"https://doi.org/10.48550/arxiv.2604.17906","title":"Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval","display_name":"Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155061739","doi":"https://doi.org/10.48550/arxiv.2604.17906"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.17906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.17906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100383368","display_name":"Junyoung Kim","orcid":"https://orcid.org/0000-0002-9007-7145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Junyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007047341","display_name":"Anton Korikov","orcid":"https://orcid.org/0009-0003-4487-9504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korikov, Anton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104197870","display_name":"Jiazhou Liang","orcid":"https://orcid.org/0009-0001-4278-8321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Jiazhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007072228","display_name":"Justin Cui","orcid":"https://orcid.org/0009-0007-7376-1256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Justin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127900191","display_name":"Yifan Simon Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yifan Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111351135","display_name":"Q. G. Wen","orcid":"https://orcid.org/0000-0002-5556-9419"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Qianfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065406046","display_name":"Mark Zhao","orcid":"https://orcid.org/0000-0002-0706-5208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Mark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134095853","display_name":"Scott Sanner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanner, Scott","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.23909999430179596,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.23909999430179596,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.14409999549388885,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11270000040531158,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7897999882698059},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6570000052452087},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5875999927520752},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.492900013923645},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.48890000581741333},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.482699990272522},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.4456999897956848}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7897999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7206000089645386},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215999722480774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5924999713897705},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5875999927520752},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.4456999897956848},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.38580000400543213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.17906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.17906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"exhibit":[5],"exceptional":[6],"zero-shot":[7],"relevance":[8,52,73,83,97,113,154],"modeling,":[9],"their":[10],"high":[11],"computational":[12],"cost":[13],"necessitates":[14],"framing":[15],"passage":[16],"retrieval":[17],"as":[18],"a":[19,76,105],"budget-constrained":[20],"global":[21,91],"optimization":[22],"problem.":[23],"Existing":[24],"approaches":[25],"passively":[26],"rely":[27],"on":[28,111,166],"first-stage":[29],"dense":[30],"retrievers,":[31],"which":[32],"leads":[33],"to":[34,39,50,54,89],"two":[35,143],"limitations:":[36],"(1)":[37],"failing":[38,49],"retrieve":[40],"relevant":[41],"passages":[42,119],"in":[43],"semantically":[44],"distinct":[45],"clusters,":[46],"and":[47,142,151,156],"(2)":[48],"propagate":[51],"signals":[53,84],"the":[55,86,95,100,125,131,162],"broader":[56],"corpus.":[57],"To":[58],"address":[59],"these":[60],"limitations,":[61],"we":[62],"propose":[63],"Bayesian":[64],"Active":[65],"Learning":[66],"with":[67,104,130],"Gaussian":[68,107],"Processes":[69],"guided":[70],"by":[71,122],"LLM":[72,82,112,144,158,164],"scoring":[74,121],"(BAGEL),":[75],"novel":[77],"framework":[78],"that":[79,147],"propagates":[80],"sparse":[81],"across":[85,99,138],"embedding":[87,102],"space":[88,103],"guide":[90],"exploration.":[92],"BAGEL":[93,148],"models":[94],"multimodal":[96],"distribution":[98],"entire":[101],"query-specific":[106],"Process":[108],"(GP)":[109],"based":[110],"scores.":[114],"Subsequently,":[115],"it":[116],"iteratively":[117],"selects":[118],"for":[120],"strategically":[123],"balancing":[124],"exploitation":[126],"of":[127,133],"high-confidence":[128],"regions":[129],"exploration":[132],"uncertain":[134],"areas.":[135],"Extensive":[136],"experiments":[137],"four":[139,168],"benchmark":[140],"datasets":[141],"backbones":[145],"demonstrate":[146],"effectively":[149],"explores":[150],"captures":[152],"complex":[153],"distributions":[155],"outperforms":[157],"reranking":[159],"methods":[160],"under":[161],"same":[163],"budget":[165],"all":[167],"datasets.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}